DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Why Your Multi-Turn AI Agents Lose Their Train of Thought (And How to Fix It)

Why Your Multi-Turn AI Agents Lose Their Train of Thought (And How to Fix It)

4
Comments 17
7 min read
My AI-agent waste detector scored zero false positives. Then I ran it on a real trace.

My AI-agent waste detector scored zero false positives. Then I ran it on a real trace.

Comments 2
6 min read
I Built an AI Agent Pipeline That Processes 10,000+ Jobs Daily. Here’s What Almost Broke It

I Built an AI Agent Pipeline That Processes 10,000+ Jobs Daily. Here’s What Almost Broke It

Comments
5 min read
Improving CRM Automation with Structured API Outputs and MegaLLM Connectors

Improving CRM Automation with Structured API Outputs and MegaLLM Connectors

2
Comments
2 min read
I spent $788 on an AI coding agent in one day. Here's the breakdown.

I spent $788 on an AI coding agent in one day. Here's the breakdown.

1
Comments
2 min read
Support Threads That Span Days: Agent Memory via Email

Support Threads That Span Days: Agent Memory via Email

Comments 2
5 min read
When to Move Beyond LiteLLM (And When Not To)

When to Move Beyond LiteLLM (And When Not To)

1
Comments
6 min read
I Built a Python Agent That Uses a Vector DB as Memory, Not Retrieval

I Built a Python Agent That Uses a Vector DB as Memory, Not Retrieval

11
Comments 8
6 min read
Claude Code Source Analysis Series, Chapter 5: Tools Overview

Claude Code Source Analysis Series, Chapter 5: Tools Overview

1
Comments
12 min read
Tool-Response Engineering: The Frontier Beyond Prompt Engineering

Tool-Response Engineering: The Frontier Beyond Prompt Engineering

Comments
17 min read
From Theory to the Floor: What Happens When "Specificity-as-Integrity" Meets a Real Restaurant

From Theory to the Floor: What Happens When "Specificity-as-Integrity" Meets a Real Restaurant

Comments
4 min read
Most RAG failures don’t crash. They silently return bad answers. I built a repair layer for that.

Most RAG failures don’t crash. They silently return bad answers. I built a repair layer for that.

Comments
1 min read
On-device LLM on iPhone: which runtime is fastest? MLX vs llama.cpp vs LiteRT-LM vs CoreML

On-device LLM on iPhone: which runtime is fastest? MLX vs llama.cpp vs LiteRT-LM vs CoreML

1
Comments 1
4 min read
我花了一下午测试了 NeuralBridge SDK:762KB 的 LLM 自愈方案,能用吗?

我花了一下午测试了 NeuralBridge SDK:762KB 的 LLM 自愈方案,能用吗?

Comments
1 min read
Gemma 4: Frontier AI in Your Hands”

Gemma 4: Frontier AI in Your Hands”

1
Comments
2 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.